Skip to main content
Glama

retry_execution

Retry failed workflow steps to resume execution from the point of failure, automatically detecting the most recent failed timeline if not specified.

Instructions

Retry a failed step in a workflow execution. If no timelineId is provided, the most recent failed timeline is automatically detected and retried. This re-runs the failed step and continues the workflow from that point.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowIdYesThe workflow ID
executionIdYesThe execution ID containing the failed step
timelineIdNoSpecific timeline ID to retry. If omitted, the most recent failed timeline is auto-detected.
forceWithoutCacheNoBypass cache when retrying the step

Implementation Reference

  • The MCP tool 'retry_execution' registration and its handler implementation in 'src/tools/executions.ts'. It uses the 'clientFactory' to call the client's 'retryExecution' method.
    server.tool(
        'retry_execution',
        `Retry a failed step in a workflow execution. If no timelineId is provided, the most recent failed timeline is automatically detected and retried. This re-runs the failed step and continues the workflow from that point.`,
        {
            workflowId: z.string().describe('The workflow ID'),
            executionId: z.string().describe('The execution ID containing the failed step'),
            timelineId: z.string().optional().describe('Specific timeline ID to retry. If omitted, the most recent failed timeline is auto-detected.'),
            forceWithoutCache: z.boolean().optional().describe('Bypass cache when retrying the step'),
        },
        async ({ workflowId, executionId, timelineId, forceWithoutCache }, extra) => {
            const client = clientFactory(extra);
            const result = await client.retryExecution(workflowId, executionId, {
                timelineId,
                forceWithoutCache,
            });
            return {
                content: [{
                    type: 'text' as const,
                    text: JSON.stringify(result, null, 2),
                }],
            };
        }
    );
  • The 'retryExecution' method in 'AgentledClient' class, which performs the actual HTTP POST request to the API to trigger the retry.
    async retryExecution(
        workflowId: string,
        executionId: string,
        options?: { timelineId?: string; forceWithoutCache?: boolean }
    ) {
        return this.request(`/workflows/${workflowId}/executions/${executionId}/retry`, {
            method: 'POST',
            body: JSON.stringify({
                timelineId: options?.timelineId,
                forceWithoutCache: options?.forceWithoutCache,
            }),
        });
    }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behaviors: automatic detection of the most recent failed timeline if timelineId is omitted, re-running the failed step, and continuing the workflow from that point. However, it lacks details on permissions, side effects, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by essential behavioral details. Both sentences earn their place by providing critical information without redundancy, making it appropriately sized and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description covers the tool's purpose, key behavior, and parameter implications adequately for a mutation tool. However, it could be more complete by mentioning potential side effects or response format, though it's sufficient for basic understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining the auto-detection behavior for timelineId ('If no timelineId is provided, the most recent failed timeline is automatically detected'), which clarifies parameter semantics beyond the schema's technical description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('retry a failed step') and resource ('workflow execution'), distinguishing it from siblings like 'start_workflow' or 'stop_execution'. It precisely defines the tool's function without being tautological.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by mentioning 'failed step' and 'workflow execution', but does not explicitly state when to use this tool versus alternatives like 'restart_workflow' or 'get_execution'. It provides some guidance but lacks explicit comparisons or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Agentled/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server